This article is a commentary on a study published in the journal Soc Sci Med 60; 2005: 2845-63. The issue of particulate matter and the health effects of chronic exposure is a topic that has attracted the attention of many researchers and addresses a growing demand for information from policymakers. Cohort studies are considered the gold standard for investigating the impact of long-term exposure to air pollution on health. Apart from the fact that they are time-consuming and costly to implement—which partly explains the scarcity of published studies—they have been criticized for the lack of representativeness of the populations studied, the lack of control over ecological variables at a relevant scale, the duration of follow-up, and inadequate control of spatial autocorrelations. Ecological cross-sectional studies, in which the unit of observation is not the individual but a group of people, offer an interesting alternative to cohort studies. The study presented in this article is part of a research program aimed at using the various available epidemiological methods (time series, cohort, cross-sectional study) to investigate the link between social factors, air pollution, and health in the Canadian city of Hamilton, Ontario. The objective of this study is to answer the following question: “Is there a significant link between chronic exposure to particulate air pollution and mortality after accounting for social determinants?” This question addresses the triangular relationship between exposure to air pollution, health effects, and social factors. In the context of the research program in which this study is situated and the theme of this issue of Extrapol, the results presented in this article are interesting because they show that, regardless of the epidemiological method used (time series, cohort, cross-sectional study), a link between long-term exposure to air pollution and mortality is evident. Beyond long-term exposure, this article presents an interesting methodology for addressing the issue of pollution’s impact in industrial cities. The reference method currently proposed in France for estimating the health impact of air pollution does not account for intra-urban variations in pollutant concentrations and socioeconomic characteristics, which are specific to industrial zones. However, as things stand, it is not possible to replicate this type of study in France because mortality data are not available at such a granular level, and furthermore, this would require local data on smoking, which is rarely the case. (Excerpts from the article)